Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add skydoves/compose-performance-skills --skill iterating-with-ai-and-mcpgit clone --depth 1 https://github.com/skydoves/compose-performance-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/skydoves/compose-performance-skills/iterating-with-ai-and-mcp)<a href="https://agentmods.dev/skills/skydoves/compose-performance-skills/iterating-with-ai-and-mcp"><img src="https://agentmods.dev/badge/skills/skydoves/compose-performance-skills/iterating-with-ai-and-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/skydoves/compose-performance-skills/iterating-with-ai-and-mcp"><img src="https://agentmods.dev/badge/skills/skydoves/compose-performance-skills/iterating-with-ai-and-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00202 | $0.02533 |
| Opus 5 | $0.00101 | $0.01267 |
| Sonnet 5 | $0.00040 | $0.00507 |
| Haiku 4.5 | $0.00020 | $0.00253 |
Grade A, and why
iterating-with-ai-and-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Iterating with AI and MCP: let the agent edit, reload, screenshot, and iterate
Compose HotSwan ships an embedded HTTP MCP server inside the IntelliJ plugin. Any MCP-compatible AI client (Claude Code, Cursor, any tool that speaks Model Context Protocol) can call its tools to drive the iteration loop. The agent edits a Kotlin file, calls hotswan_reload, captures a screenshot of the running device, evaluates the result against the design intent, and decides the next change. Cycle time is comparable to the human loop, a few seconds per iteration, so the agent can converge on a UI tweak without a human steering each step.
This skill teaches the canonical agent loop, the seven MCP tools (verbatim names), and the safety habits (status check first, snapshot wrapping for rollback, fallback to full install for schema changes) that keep the loop reliable.
When to use this skill
- The developer wants AI-driven UI iteration: "tune this screen until it matches the mock", "let the agent pick a colour".
- The developer wants the AI to verify its own edits visually instead of guessing whether the change worked.
- The developer is wiring up a Claude Code or Cursor workflow that needs MCP tool access to a running app.
- The user asks "can the AI see what changed?", "can the AI screenshot the device?", "how does Claude Code drive HotSwan?".
- The user mentions "MCP server", "hotswan_reload", "hotswan_take_screenshot", "agent loop", or "snapshot rollback".
When NOT to use this skill
- Pure code review without runtime feedback (no need for MCP tools at all).
- Release-grade visual regression testing. Use Macrobenchmark plus a screenshot diff harness, not HotSwan snapshots. Cross-link
../../measurement/generating-baseline-profiles/SKILL.md. - The change in question would force a full rebuild (parameter add, constructor change, new resource ID). Read
../understanding-hot-reload-limits/SKILL.mdfirst to classify the edit before reaching for the MCP loop. - The reload keeps escalating to tier 2 or tier 3 and losing state. Fix that with
../preserving-state-across-reloads/SKILL.mdbefore adding an autonomous loop on top.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 187 lines · 202 tokens per session scan A 60502d01fff5
iterating-with-ai-and-mcp is a skill published in the GitHub repository skydoves/compose-performance-skills (502 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 202 tokens to every session and 2,533 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
claude-android-ninja
Build and migrate Android apps with Kotlin, Jetpack Compose, MVVM, Hilt, Room 3 (KSP, SQLiteDriver, Flow/suspend DAOs), Navigation3, and multi-module Gradle. Use for new projects or modules, Compose screens and ViewModels, Room 3 and RemoteMediator, API 37 / targetSdk migration, Play Integrity client wiring…
compose-animations
Use when writing or reviewing Jetpack Compose motion: visibility enter/exit, animating one property toward a target, color or size transitions, multiple properties from one state, switching composable content, or choosing between AnimatedVisibility, animateAsState, rememberTransition, AnimatedContent, and Crossfade.
compose-focus-navigation
Use when writing or reviewing Jetpack Compose UI for TV, keyboard, desktop, accessibility focus, D-pad navigation, FocusRequester, focusProperties, key events, or initial focus behavior.
kotlin-android
Use when building or fixing a native Android app in Kotlin and Jetpack Compose on the UDF layered architecture — ViewModel/StateFlow, Hilt, Room, Retrofit, coroutines, type-safe Navigation, and the Gradle/AGP surface. NOT shared Android and iOS UI from one Kotlin codebase (that is compose-multiplatform).
compose-side-effects
Use when writing or reviewing Jetpack Compose code with LaunchedEffect, DisposableEffect, SideEffect, rememberCoroutineScope, rememberUpdatedState, snapshotFlow, snackbar, navigation, focus requests, analytics, or event Flow collection.
deliver-android-feature
Implement an Android feature from a specification or acceptance criteria through architecture, production code, formatting, unit tests, JVM integration tests, local Compose behavior tests, screenshot matrices, managed-device integration tests, end-to-end coverage, and final verification. Use when adding or…